library(tidyverse)
## ── Attaching core tidyverse packages ──────────────────────── tidyverse 2.0.0 ──
## ✔ dplyr 1.1.2 ✔ readr 2.1.4
## ✔ forcats 1.0.0 ✔ stringr 1.5.0
## ✔ ggplot2 3.4.2 ✔ tibble 3.2.1
## ✔ lubridate 1.9.2 ✔ tidyr 1.3.0
## ✔ purrr 1.0.1
## ── Conflicts ────────────────────────────────────────── tidyverse_conflicts() ──
## ✖ dplyr::filter() masks stats::filter()
## ✖ dplyr::lag() masks stats::lag()
## ℹ Use the conflicted package (<http://conflicted.r-lib.org/>) to force all conflicts to become errors
library(plotly)
##
## Attaching package: 'plotly'
##
## The following object is masked from 'package:ggplot2':
##
## last_plot
##
## The following object is masked from 'package:stats':
##
## filter
##
## The following object is masked from 'package:graphics':
##
## layout
library(p8105.datasets)
Focus on NYC Airbnb data.
data("nyc_airbnb")
nyc_airbnb =
nyc_airbnb |>
mutate(stars= review_scores_location/ 2) |>
select(borough= neighbourhood_group, neighbourhood,stars, price,
room_type, lat, long) |>
drop_na(stars) |>
filter(
borough == "Manhattan",
room_type == "Entire home/apt",
price %in% 100:500
)
drop_na() can drop anything with the variable that is
NA.
Scaterrplot!
nyc_airbnb |>
mutate(text_label= str_c("Price: $", price, "\nRating: ", stars)) |>
plot_ly(
x = ~lat, y = ~long, color= ~price, text=~text_label,
type= "scatter", mode= "markers", alpha= 0.5)
str_c = string combine `str_c(“Label for variable”,
variable name, “Label for variable”, variable name)) = new line
Let’s do BOX PLOT
nyc_airbnb |>
plot_ly(y = ~price, color = ~neighbourhood, type = "box", colors = "viridis")
nyc_airbnb |>
mutate(neighbourhood = fct_reorder(neighbourhood, price)) |>
plot_ly(y = ~price, color = ~neighbourhood, type = "box", colors = "viridis")
BAR PLOT
nyc_airbnb |>
count(neighbourhood) |>
mutate(neighbourhood = fct_reorder(neighbourhood, n)) |>
plot_ly(
x = ~neighbourhood, y= ~n, color= ~neighbourhood, type= "bar", colors= "viridis")